2022/03/13 by Anusha Damodaran, Fabio Di Troia, Visaggio Aaron Corrado +2 · 1 citation
Computer Science · #cs.CR #cs.LG
paper · pdf · doi:10.1007/s11416-015-0261-z
published as J Comput Virol Hack Tech 13, 1–12 (2017)
arxiv created 2022/03/13 · arxiv updated 2022/03/21
In this research, we compare malware detection techniques based on static, dynamic, and hybrid analysis. Specifically, we train Hidden Markov Models (HMMs ) on both static and dynamic feature sets and compare the resulting detection rates over a substantial number of malware families. We also consider hybrid cases, where dynamic analysis is used in the training phase, with static techniques used in the detection phase, and vice versa. In our experiments, a fully dynamic approach generally yields the best detection rates. We discuss the implications of this research for malware detection based on hybrid techniques.